ResearchTasksGeneral Multi-image Reasoning and GeneralizationGeneral Multi-image Reasoning and GeneralizationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedLLaVA-Interleave Bench Out-domainGPT-4V57.8Average Score7Feb 26, 2026